The factors determining the suitability of limestone for industrial use and its commercial value are the amounts of calcium oxide (CaO) and impurities. From 244 sample points in 18 drillhole sites in a limestone mine, southwestern Japan, data on four impurity elements, SiO2, Fe2O3, MnO, and P2O5 were collected. It generally is difficult to estimate spatial distributions of these contents, because most of the limestone bodies in Japan are located in the accretionary complex lithologies of Paleozoic and Mesozoic age. Because the spatial correlations of content data are not clearly shown by variogram analysis, a feedforward neural network was applied to estimate the content distributions. The network structure consists of three layers: input, middle, and output. The input layer has 17 neurons and the output layer four. Three neurons in the input layer correspond with x, y, z coordinates of a sample point and the others are rock types such as crystalline and conglomeratic limestones, and fossil types related to the geologic age of the limestone. Four neurons in the output layer correspond to the amounts of SiO2, Fe2O3, MnO, and P2O5. Numbers of neurons in the middle layer and training data differ with each estimation point to avoid the overfitting of the network. We could detect several important characteristics of the three-dimensional content distributions through the network such as a continuity of low content zones of SiO2 along a Lower Permian fossil zone trending NE-SW, and low-quality zones located in depths shallower than 50 m. The capability of the neural network-based method compared with the geostatistical method is demonstrated from the viewpoints of estimation errors and spatial characteristics of multivariate data. To evaluate the uncertainty of estimates, a method that draws several outputs by changing coordinates slightly from the target point and inputting them to the same trained network is proposed. Uncertainty differs with impurity elements, and is not based on just the spatial arrangement of data points.
[1]
Geoffrey E. Hinton,et al.
Learning representations by back-propagating errors
,
1986,
Nature.
[2]
Geoffrey E. Hinton,et al.
Learning representations by back-propagation errors, nature
,
1986
.
[3]
H. Sano,et al.
Paleogeographic reconstruction of accreted oceanic rocks, Akiyoshi, southwest Japan
,
1988
.
[4]
A. Taira,et al.
Accretion tectonics and evolution of Japan
,
1989
.
[5]
Quality mapping of the Ryytimaa dolomite in western Finland
,
1996
.
[6]
Javier Taboada,et al.
Application of geostatistical techniques to exploitation planning in slate quarries
,
1997
.
[7]
Ángeles Saavedra,et al.
Quality index for ornamental slate deposits
,
1998
.
[8]
Katsuaki Koike,et al.
Three-Dimensional Interpolation and Lithofacies Analysis of Granular Composition Data for Earthquake-Engineering Characterization of Shallow Soil
,
1998
.
[9]
Michito Ohmi,et al.
Three-dimensional distribution analysis of phosphorus content of limestone through a combination of geostatistics and artificial neural network
,
1998
.
[10]
Michito Ohmi,et al.
Neural Network-Based Estimation of Principal Metal Contents in the Hokuroku District, Northern Japan, for Exploring Kuroko-Type Deposits
,
2002
.